snigdhachandan commited on
Commit
af68e9c
1 Parent(s): 00badd9

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - deepseek-ai/deepseek-math-7b-rl
7
+ - meta-math/MetaMath-7B-V1.0
8
+ base_model:
9
+ - deepseek-ai/deepseek-math-7b-rl
10
+ - meta-math/MetaMath-7B-V1.0
11
+ ---
12
+
13
+ # ganeet-V2
14
+
15
+ ganeet-V2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [deepseek-ai/deepseek-math-7b-rl](https://huggingface.co/deepseek-ai/deepseek-math-7b-rl)
17
+ * [meta-math/MetaMath-7B-V1.0](https://huggingface.co/meta-math/MetaMath-7B-V1.0)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: deepseek-ai/deepseek-math-7b-rl
25
+ layer_range: [0, 30]
26
+ - model: meta-math/MetaMath-7B-V1.0
27
+ layer_range: [0, 30]
28
+ merge_method: slerp
29
+ base_model: deepseek-ai/deepseek-math-7b-rl
30
+ parameters:
31
+ t:
32
+ - filter: self_attn
33
+ value: [0, 0.5, 0.3, 0.7, 1]
34
+ - filter: mlp
35
+ value: [1, 0.5, 0.7, 0.3, 0]
36
+ - value: 0.4
37
+ dtype: bfloat16
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "snigdhachandan/ganeet-V2"
50
+ messages = [{"role": "user", "content": "What is a large language model?"}]
51
+
52
+ tokenizer = AutoTokenizer.from_pretrained(model)
53
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
+ pipeline = transformers.pipeline(
55
+ "text-generation",
56
+ model=model,
57
+ torch_dtype=torch.float16,
58
+ device_map="auto",
59
+ )
60
+
61
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
62
+ print(outputs[0]["generated_text"])
63
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 100000,
9
+ "eos_token_id": 100001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "moe_intermediate_size": 11008,
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 30,
19
+ "num_key_value_heads": 32,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.38.2",
27
+ "use_cache": true,
28
+ "vocab_size": 102400
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: deepseek-ai/deepseek-math-7b-rl
5
+ layer_range: [0, 30]
6
+ - model: meta-math/MetaMath-7B-V1.0
7
+ layer_range: [0, 30]
8
+ merge_method: slerp
9
+ base_model: deepseek-ai/deepseek-math-7b-rl
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.4
17
+ dtype: bfloat16
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd3789ea4790bca945712b9f36d1c687cca320d3a3f415d2d990046bbba7916
3
+ size 929080656
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734d55c6fa9127e8c344ce564666bb4f6889cf2f7d61961448d490bb59615c9b
3
+ size 989890832
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac96e7ad8acffcb9031da7f8b7160652648e0938d5b77e8f002804ccb152108f
3
+ size 966830592
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8465b7c88efdb864001f7e549c26889cc9d5ff30f3cd8e0cc5955acd257a91ab
3
+ size 966830584
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0186b16d46569d98b10e89924b1850e70c010c13389368daf4b07deec53f9e72
3
+ size 989899152
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5024c2d108d4867bdbe5eb69b4fd4784c62ca4ac4eb6bf257b8eea661e48895a
3
+ size 943762024
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af3d3ff760af015c2e1d015a07631a820d57e652eb928a7ab3e2675f5bdeb0b
3
+ size 989890840
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd1a66fb029b0dd09b75ac6720220a6ef8bc46eb4b34f5279de86e407da6d0d
3
+ size 966830592
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa153fa509e4ddf8dc159ec03f5cdb26df873efc246fa1e2e6e0d4100e91a79
3
+ size 966830584
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b631d99c963e628ae819a16cff4b780bd09f7858228aa3b36dc4d4415b72d397
3
+ size 989899152
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e48b0623cfe249b88d270c9dcc65d1ebd1106091ade24efb89aa9a635405b1
3
+ size 943762016
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf4ae7aeeeb147001a38122976e0534361679f6d8a87c84680904ed39ab795d
3
+ size 989890816
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83402b9915cec727ba8347a79c60b04b665cf05bb1ec94080576767e1b703823
3
+ size 966830568
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c4455675e63d23b501ae4e7c80f2366ad56261c92abbb8b0fcf3df24cb1d8b
3
+ size 67117408
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 12667314176}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "100000": {
6
+ "content": "<|begin▁of▁sentence|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100001": {
14
+ "content": "<|end▁of▁sentence|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "<|begin▁of▁sentence|>",
23
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
24
+ "clean_up_tokenization_spaces": false,
25
+ "eos_token": "<|end▁of▁sentence|>",
26
+ "legacy": true,
27
+ "model_max_length": 4096,
28
+ "sp_model_kwargs": {},
29
+ "tokenizer_class": "LlamaTokenizer",
30
+ "unk_token": null,
31
+ "use_default_system_prompt": false
32
+ }